Agentic V2X Communications: Goal-Aware Information Exchange, Semantic Coordination, and Autonomous Decision-Making in 6G Vehicular Networks

Abstract

6G research increasingly treats vehicular communicationas an active, goal-driven substrate rather than a passivepipe for bits. This survey examines Agentic Vehicle-to-Everything(V2X) Communications, where vehicles and roadside entities actas autonomous agents that exchange information according to itsvalue toward explicit goals (goal-aware information exchange),share a common semantic picture of the driving scene (semanticcoordination), and reach distributed decisions inside explicitsafety, trust, and interoperability bounds (autonomous decisionmaking).Working from an explicit search methodology, we placethe survey against 27 related works along ten dimensions and findthat none brings these threads together within a single vehicularframework. We formalize what an agentic V2X entity is, introducea nine-criterion qualification table on which no surveyedvehicular system class scores more than four, and organize theliterature into a five-layer taxonomy that runs from 6G enablersthrough value-of-information scheduling, ontology-based semanticcoordination and negotiation, up to multi-agent reinforcementlearning (MARL) and large language model (LLM) reasoninggated by a formally scoped safety shield. Three reproduciblenumerical studies make the mechanisms concrete: value-ofinformationscheduling compared against fixed-periodicity andage-of-information baselines, the way negotiation converges asthe number of agents grows, and a control-barrier-function shieldwhose guarantee holds only within its assumed sensing bound.We propose a reference architecture, work through use cases andwhere they stop being appropriate, separate safety from securityby way of a threat taxonomy, set out a six-category evaluationtaxonomy, map standardization needs onto existing bodies, andclose with fourteen open challenges and a roadmap.